forked from eriklindernoren/PyTorch-GAN
-
Notifications
You must be signed in to change notification settings - Fork 0
/
aae.py
211 lines (163 loc) · 6.46 KB
/
aae.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
import argparse
import os
import numpy as np
import math
import itertools
import torchvision.transforms as transforms
from torchvision.utils import save_image
from torch.utils.data import DataLoader
from torchvision import datasets
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
import torch
os.makedirs("images", exist_ok=True)
parser = argparse.ArgumentParser()
parser.add_argument("--n_epochs", type=int, default=200, help="number of epochs of training")
parser.add_argument("--batch_size", type=int, default=64, help="size of the batches")
parser.add_argument("--lr", type=float, default=0.0002, help="adam: learning rate")
parser.add_argument("--b1", type=float, default=0.5, help="adam: decay of first order momentum of gradient")
parser.add_argument("--b2", type=float, default=0.999, help="adam: decay of first order momentum of gradient")
parser.add_argument("--n_cpu", type=int, default=8, help="number of cpu threads to use during batch generation")
parser.add_argument("--latent_dim", type=int, default=10, help="dimensionality of the latent code")
parser.add_argument("--img_size", type=int, default=32, help="size of each image dimension")
parser.add_argument("--channels", type=int, default=1, help="number of image channels")
parser.add_argument("--sample_interval", type=int, default=400, help="interval between image sampling")
opt = parser.parse_args()
print(opt)
img_shape = (opt.channels, opt.img_size, opt.img_size)
cuda = True if torch.cuda.is_available() else False
def reparameterization(mu, logvar):
std = torch.exp(logvar / 2)
sampled_z = Variable(Tensor(np.random.normal(0, 1, (mu.size(0), opt.latent_dim))))
z = sampled_z * std + mu
return z
class Encoder(nn.Module):
def __init__(self):
super(Encoder, self).__init__()
self.model = nn.Sequential(
nn.Linear(int(np.prod(img_shape)), 512),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 512),
nn.BatchNorm1d(512),
nn.LeakyReLU(0.2, inplace=True),
)
self.mu = nn.Linear(512, opt.latent_dim)
self.logvar = nn.Linear(512, opt.latent_dim)
def forward(self, img):
img_flat = img.view(img.shape[0], -1)
x = self.model(img_flat)
mu = self.mu(x)
logvar = self.logvar(x)
z = reparameterization(mu, logvar)
return z
class Decoder(nn.Module):
def __init__(self):
super(Decoder, self).__init__()
self.model = nn.Sequential(
nn.Linear(opt.latent_dim, 512),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 512),
nn.BatchNorm1d(512),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, int(np.prod(img_shape))),
nn.Tanh(),
)
def forward(self, z):
img_flat = self.model(z)
img = img_flat.view(img_flat.shape[0], *img_shape)
return img
class Discriminator(nn.Module):
def __init__(self):
super(Discriminator, self).__init__()
self.model = nn.Sequential(
nn.Linear(opt.latent_dim, 512),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 256),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(256, 1),
nn.Sigmoid(),
)
def forward(self, z):
validity = self.model(z)
return validity
# Use binary cross-entropy loss
adversarial_loss = torch.nn.BCELoss()
pixelwise_loss = torch.nn.L1Loss()
# Initialize generator and discriminator
encoder = Encoder()
decoder = Decoder()
discriminator = Discriminator()
if cuda:
encoder.cuda()
decoder.cuda()
discriminator.cuda()
adversarial_loss.cuda()
pixelwise_loss.cuda()
# Configure data loader
os.makedirs("../../data/mnist", exist_ok=True)
dataloader = torch.utils.data.DataLoader(
datasets.MNIST(
"../../data/mnist",
train=True,
download=True,
transform=transforms.Compose(
[transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])]
),
),
batch_size=opt.batch_size,
shuffle=True,
)
# Optimizers
optimizer_G = torch.optim.Adam(
itertools.chain(encoder.parameters(), decoder.parameters()), lr=opt.lr, betas=(opt.b1, opt.b2)
)
optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
def sample_image(n_row, batches_done):
"""Saves a grid of generated digits"""
# Sample noise
z = Variable(Tensor(np.random.normal(0, 1, (n_row ** 2, opt.latent_dim))))
gen_imgs = decoder(z)
save_image(gen_imgs.data, "images/%d.png" % batches_done, nrow=n_row, normalize=True)
# ----------
# Training
# ----------
for epoch in range(opt.n_epochs):
for i, (imgs, _) in enumerate(dataloader):
# Adversarial ground truths
valid = Variable(Tensor(imgs.shape[0], 1).fill_(1.0), requires_grad=False)
fake = Variable(Tensor(imgs.shape[0], 1).fill_(0.0), requires_grad=False)
# Configure input
real_imgs = Variable(imgs.type(Tensor))
# -----------------
# Train Generator
# -----------------
optimizer_G.zero_grad()
encoded_imgs = encoder(real_imgs)
decoded_imgs = decoder(encoded_imgs)
# Loss measures generator's ability to fool the discriminator
g_loss = 0.001 * adversarial_loss(discriminator(encoded_imgs), valid) + 0.999 * pixelwise_loss(
decoded_imgs, real_imgs
)
g_loss.backward()
optimizer_G.step()
# ---------------------
# Train Discriminator
# ---------------------
optimizer_D.zero_grad()
# Sample noise as discriminator ground truth
z = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))
# Measure discriminator's ability to classify real from generated samples
real_loss = adversarial_loss(discriminator(z), valid)
fake_loss = adversarial_loss(discriminator(encoded_imgs.detach()), fake)
d_loss = 0.5 * (real_loss + fake_loss)
d_loss.backward()
optimizer_D.step()
print(
"[Epoch %d/%d] [Batch %d/%d] [D loss: %f] [G loss: %f]"
% (epoch, opt.n_epochs, i, len(dataloader), d_loss.item(), g_loss.item())
)
batches_done = epoch * len(dataloader) + i
if batches_done % opt.sample_interval == 0:
sample_image(n_row=10, batches_done=batches_done)